© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17164
    Prev
    Next
    INDEX
    Explanations

    proteasome, synthase, oxidase complexes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arki
    -0.08
    æ®ĥ
    -0.07
    工信
    -0.07
    å®ŀæĸ½åĬŀæ³ķ
    -0.07
    åĬ²åĦ¿
    -0.07
    ly
    -0.07
     fuss
    -0.07
    ERAH
    -0.07
    ко
    -0.07
     choices
    -0.07
    POSITIVE LOGITS
    ç»ĦæĪIJ
    0.07
    ç»Ħ件
    0.07
    解ä½ĵ
    0.07
    çµĦæĪIJ
    0.07
     composed
    0.07
     ÑģоÑģÑĤаве
    0.07
    主ä½ĵç»ĵæŀĦ
    0.07
     elaborate
    0.07
    ç»ĦåĪĨ
    0.07
    composed
    0.07
    Activations Density 0.029%

    No Known Activations